[Feature]: Transcript Editing Before Audio Generation

[endorphina]

Feature Description

Hi Open Notebook team, I’m a huge fan of what you’ve built with Open Notebook – the workflow from documents to conversational podcasts is really impressive! I’ve been using it locally with Ollama and have had a great experience. One feature I’d love to see is the ability to edit the generated transcript before it’s converted to audio. Currently, I generate transcripts, but there’s no interface to refine them (fix tone, adjust dialogue, remove filler words, etc.) before the final audio export.

Thanks for the awesome project! Happy to help test or provide feedback on this feature. Best regards

Why would this be helpful?

Having a simple transcript editor – even just a basic text interface with timestamps – would make the workflow complete. It would allow us to: • Fine-tune dialogue and pacing • Correct any AI-generated quirks • Adjust speaker interjections • Maintain quality control before audio generation

Additional Context

No response

[lfnovo]

This is a good idea that makes sense to do some time soon. It does require some redesigning so we'll keep it here until someone can take a look into it.